test(app): multi-scanned PDF chunk_id collision-free integration test (Bug #3 regression)

v0.20.0 sub-item 1 bugfix Step 3 (Group C) — integration-level regression
for Bug #3 (intra-doc chunk_id collision under aggressive overlap).

- `crates/kebab-app/tests/common/mod.rs`: `pub mod mock_ocr;` 1 line append.
- `crates/kebab-app/tests/common/mock_ocr.rs` (new): MockOcrEngine lift +
  `single` / `per_page` ctor (backward-compat single + per-page cursor).
- `crates/kebab-app/tests/pdf_ocr_apply.rs`: inline MockOcrEngine 제거 +
  `mod common; use common::mock_ocr::MockOcrEngine;` import. 10 ctor call
  site migration (`MockOcrEngine { .. }` → `MockOcrEngine::single(...)`).
- `crates/kebab-app/tests/multi_scanned_pdf_ingest_no_chunk_id_collision.rs`
  (new): F1 + F2 scanned PDF + Bug #3 trigger shape (10 char "가" + ". " +
  500 char "나") via mock OCR. assertion: chunk_id global uniqueness (HashSet
  dedup) across F1 + F2; F2 trigger text produces ≥2 chunks (collision shape).
- C1 decision: Option A (share via tests/common/mock_ocr.rs). Facade mock
  injection unavailable (OllamaVisionOcr hardcoded) — helper-level chain test
  (apply_ocr_to_pdf_pages → PdfPageV1Chunker) adds value beyond unit B5.

spec: docs/superpowers/specs/2026-05-27-v0.20-sub1-bugfix-spec.md (§4.5)
plan: docs/superpowers/plans/2026-05-27-v0.20-sub1-bugfix-plan.md (Step 3)
prior: 436fd01 (Step 2 Bug #3 chunk_id fix)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

crates/kebab-app/tests/common/mock_ocr.rs

@@ -0,0 +1,60 @@
+use std::sync::Mutex;
+
+use anyhow::Result;
+use kebab_core::{Lang, OcrText};
+use kebab_parse_image::OcrEngine;
+
+pub struct MockOcrEngine {
+    expected_texts: Vec<String>,
+    call_index: Mutex<usize>,
+    fail: bool,
+}
+
+impl MockOcrEngine {
+    /// Single text (backward-compat ctor for pdf_ocr_apply.rs 10 sites).
+    pub fn single(text: impl Into<String>, fail: bool) -> Self {
+        Self {
+            expected_texts: vec![text.into()],
+            call_index: Mutex::new(0),
+            fail,
+        }
+    }
+
+    /// Per-page texts (cursor advances per recognize call).
+    pub fn per_page(texts: Vec<String>, fail: bool) -> Self {
+        Self {
+            expected_texts: texts,
+            call_index: Mutex::new(0),
+            fail,
+        }
+    }
+}
+
+impl OcrEngine for MockOcrEngine {
+    fn engine_name(&self) -> &'static str {
+        "mock-ocr"
+    }
+
+    fn engine_version(&self) -> String {
+        "mock-v1".to_string()
+    }
+
+    fn recognize(&self, _img: &[u8], _hint: Option<&Lang>) -> Result<OcrText> {
+        if self.fail {
+            anyhow::bail!("mock failure");
+        }
+        let mut idx = self.call_index.lock().unwrap();
+        let text = self
+            .expected_texts
+            .get(*idx)
+            .cloned()
+            .unwrap_or_else(|| self.expected_texts.last().cloned().unwrap_or_default());
+        *idx += 1;
+        Ok(OcrText {
+            joined: text,
+            regions: vec![],
+            engine: "mock-ocr".to_string(),
+            engine_version: "mock-v1".to_string(),
+        })
+    }
+}

crates/kebab-app/tests/common/mod.rs

@@ -169,3 +169,5 @@ fn copy_dir_recursive(src: &Path, dest: &Path) {
         }
     }
 }
+
+pub mod mock_ocr;

crates/kebab-app/tests/multi_scanned_pdf_ingest_no_chunk_id_collision.rs

@@ -0,0 +1,122 @@
+//! Bug #3 regression: multi-scanned PDF ingest must produce globally unique chunk_ids.
+//! v0.20.0 sub-item 1 bugfix.
+//!
+//! Strategy: helper-level chain test (apply_ocr_to_pdf_pages → PdfPageV1Chunker).
+//! Facade mock injection is unavailable (kebab-app hardcodes OllamaVisionOcr), so
+//! this test covers the full OCR→chunk pipeline with real PDF fixtures + MockOcrEngine,
+//! adding value beyond kebab-chunk unit test B5 (which tests PdfPageV1Chunker alone).
+
+mod common;
+
+use std::collections::HashSet;
+use std::path::{Path, PathBuf};
+
+use common::mock_ocr::MockOcrEngine;
+use kebab_app::pdf_ocr_apply::{PdfOcrOpts, apply_ocr_to_pdf_pages};
+use kebab_chunk::PdfPageV1Chunker;
+use kebab_core::{
+    AssetStorage, Checksum, ChunkPolicy, Chunker, ExtractConfig, ExtractContext, Extractor,
+    MediaType, RawAsset, SourceUri, WorkspacePath, id_for_asset,
+};
+use kebab_parse_image::OcrEngine;
+use kebab_parse_pdf::PdfTextExtractor;
+use time::OffsetDateTime;
+
+fn make_pdf_asset(path: &str, hash_char: char, byte_len: u64) -> RawAsset {
+    let fake_hash: String = hash_char.to_string().repeat(64);
+    let asset_id = id_for_asset(&fake_hash);
+    RawAsset {
+        asset_id,
+        source_uri: SourceUri::File(PathBuf::from(path)),
+        workspace_path: WorkspacePath::new(path.to_string()).unwrap(),
+        media_type: MediaType::Pdf,
+        byte_len,
+        checksum: Checksum(fake_hash),
+        discovered_at: OffsetDateTime::UNIX_EPOCH,
+        stored: AssetStorage::Copied {
+            path: PathBuf::from(path),
+        },
+    }
+}
+
+fn extract_and_ocr(
+    bytes: &[u8],
+    path: &str,
+    hash_char: char,
+    engine: &dyn OcrEngine,
+) -> kebab_core::CanonicalDocument {
+    let asset = make_pdf_asset(path, hash_char, bytes.len() as u64);
+    let workspace_root = Path::new("/");
+    let config = ExtractConfig::default();
+    let ctx = ExtractContext {
+        asset: &asset,
+        workspace_root,
+        config: &config,
+    };
+    let mut canonical = PdfTextExtractor::new().extract(&ctx, bytes).unwrap();
+    let opts = PdfOcrOpts {
+        enabled: true,
+        always_on: false,
+        valid_ratio_threshold: 0.5,
+        min_char_count: 20,
+        lang_hint: None,
+        cancel: None,
+    };
+    apply_ocr_to_pdf_pages(&mut canonical, engine, bytes, &opts, |_| {}).unwrap();
+    canonical
+}
+
+#[test]
+fn multi_scanned_pdf_ingest_no_chunk_id_collision() {
+    let f1_bytes = std::fs::read("../kebab-parse-pdf/tests/fixtures/scanned_page1.pdf")
+        .expect("F1 fixture missing");
+    let f2_bytes = std::fs::read("../kebab-parse-pdf/tests/fixtures/scanned_page2.pdf")
+        .expect("F2 fixture missing");
+
+    // Bug #3 trigger shape: 10-char early segment + ". " + 500-char tail.
+    // byte_len = 10*3 + 2 + 500*3 = 1532 > target_bytes=1500 → multi-chunk.
+    // overlap_bytes = min(240, 750) = 240 / chars=80 → second chunk's actual_start
+    // collapses to prev_min=0 without the fix → same #c0 suffix → chunk_id collision.
+    let trigger_text = format!("{}. {}", "가".repeat(10), "나".repeat(500));
+
+    let f1_engine = MockOcrEngine::single("F1 mock OCR page text", false);
+    let f2_engine = MockOcrEngine::single(&trigger_text, false);
+
+    let f1_canonical = extract_and_ocr(&f1_bytes, "page1.pdf", '1', &f1_engine);
+    let f2_canonical = extract_and_ocr(&f2_bytes, "page2.pdf", '2', &f2_engine);
+
+    let chunk_policy = ChunkPolicy {
+        target_tokens: 500,
+        overlap_tokens: 80,
+        respect_markdown_headings: false,
+        chunker_version: PdfPageV1Chunker.chunker_version(),
+    };
+
+    let f1_chunks = PdfPageV1Chunker
+        .chunk(&f1_canonical, &chunk_policy)
+        .unwrap();
+    let f2_chunks = PdfPageV1Chunker
+        .chunk(&f2_canonical, &chunk_policy)
+        .unwrap();
+
+    assert!(
+        f2_chunks.len() >= 2,
+        "F2 trigger text must produce ≥2 chunks for the collision to be possible; got {}",
+        f2_chunks.len()
+    );
+
+    let all_ids: Vec<&str> = f1_chunks
+        .iter()
+        .chain(f2_chunks.iter())
+        .map(|c| c.chunk_id.0.as_str())
+        .collect();
+    let total = all_ids.len();
+    let unique: HashSet<&str> = all_ids.iter().copied().collect();
+    assert_eq!(
+        unique.len(),
+        total,
+        "all chunk_ids must be globally unique across F1 + F2 ({} unique vs {} total — collision detected)",
+        unique.len(),
+        total,
+    );
+}

crates/kebab-app/tests/pdf_ocr_apply.rs

@@ -1,49 +1,21 @@
 //! Integration tests for pdf_ocr_apply helper. spec §5.5 MockOcrEngine pattern.
 
+mod common;
+
 use std::path::{Path, PathBuf};
 use std::sync::Arc;
 use std::sync::atomic::AtomicBool;
 
-use anyhow::Result;
+use common::mock_ocr::MockOcrEngine;
 use kebab_app::pdf_ocr_apply::{PdfOcrOpts, apply_ocr_to_pdf_pages};
 use kebab_core::{
     AssetStorage, Block, CanonicalDocument, Checksum, ExtractConfig, ExtractContext,
-    Extractor, Inline, Lang, MediaType, OcrText, RawAsset, SourceSpan,
+    Extractor, Inline, Lang, MediaType, RawAsset, SourceSpan,
     SourceUri, WorkspacePath, id_for_asset,
 };
-use kebab_parse_image::OcrEngine;
 use kebab_parse_pdf::PdfTextExtractor;
 use time::OffsetDateTime;
 
-// ── MockOcrEngine fixture ─────────────────────────────────────────────────
-
-struct MockOcrEngine {
-    expected_text: String,
-    fail: bool,
-}
-
-impl OcrEngine for MockOcrEngine {
-    fn engine_name(&self) -> &'static str {
-        "mock-ocr"
-    }
-
-    fn engine_version(&self) -> String {
-        "mock-v1".to_string()
-    }
-
-    fn recognize(&self, _img: &[u8], _hint: Option<&Lang>) -> Result<OcrText> {
-        if self.fail {
-            anyhow::bail!("mock failure");
-        }
-        Ok(OcrText {
-            joined: self.expected_text.clone(),
-            regions: Vec::new(),
-            engine: self.engine_name().to_string(),
-            engine_version: self.engine_version(),
-        })
-    }
-}
-
 // ── Fixture helpers ───────────────────────────────────────────────────────
 
 fn f1_pdf_bytes() -> Vec<u8> {
@@ -136,10 +108,7 @@ fn default_opts(enabled: bool) -> PdfOcrOpts {
 fn f1_input_with_ocr_enabled_replaces_empty_block() {
     let bytes = f1_pdf_bytes();
     let mut canonical = canonical_with_empty_block();
-    let engine = MockOcrEngine {
+    let engine = MockOcrEngine::single("MOCK_OCR_TEXT", false);
-        expected_text: "MOCK_OCR_TEXT".into(),
-        fail: false,
-    };
     let opts = PdfOcrOpts {
         enabled: true,
         always_on: false,
@@ -166,10 +135,7 @@ fn f3_input_with_ocr_enabled_keeps_text_detect_blocks() {
     let bytes = f1_pdf_bytes(); // reuse F1 bytes; decision is based on canonical text
     let text = "충분한 한국어 텍스트 컨텐츠입니다. This has more than twenty characters.";
     let mut canonical = canonical_with_filled_block(text);
-    let engine = MockOcrEngine {
+    let engine = MockOcrEngine::single("SHOULD_NOT_BE_CALLED", false);
-        expected_text: "SHOULD_NOT_BE_CALLED".into(),
-        fail: false,
-    };
     let opts = default_opts(true);
 
     let summary = apply_ocr_to_pdf_pages(&mut canonical, &engine, &bytes, &opts, |_| {}).unwrap();
@@ -189,10 +155,7 @@ fn f3_input_with_ocr_enabled_keeps_text_detect_blocks() {
 fn f1_input_with_ocr_disabled_keeps_empty_block() {
     let bytes = f1_pdf_bytes();
     let mut canonical = canonical_with_empty_block();
-    let engine = MockOcrEngine {
+    let engine = MockOcrEngine::single("IGNORED", false);
-        expected_text: "IGNORED".into(),
-        fail: false,
-    };
     let opts = default_opts(false);
 
     let summary = apply_ocr_to_pdf_pages(&mut canonical, &engine, &bytes, &opts, |_| {}).unwrap();
@@ -206,10 +169,7 @@ fn f1_input_with_ocr_disabled_keeps_empty_block() {
 fn f4_input_with_ocr_enabled_replaces_mojibake_block() {
     let bytes = f1_pdf_bytes(); // F1 bytes carry DCTDecode image
     let mut canonical = canonical_with_mojibake_block();
-    let engine = MockOcrEngine {
+    let engine = MockOcrEngine::single("OCR_MOJIBAKE_REPLACEMENT", false);
-        expected_text: "OCR_MOJIBAKE_REPLACEMENT".into(),
-        fail: false,
-    };
     let opts = PdfOcrOpts {
         enabled: true,
         always_on: false,
@@ -238,10 +198,7 @@ fn f3_input_with_always_on_pushes_dual_blocks() {
     let text = "vector PDF 충분한 텍스트 컨텐츠입니다. This has enough characters for valid ratio.";
     let mut canonical = canonical_with_filled_block(text);
     let original_block_count = canonical.blocks.len();
-    let engine = MockOcrEngine {
+    let engine = MockOcrEngine::single("OCR_DUAL", false);
-        expected_text: "OCR_DUAL".into(),
-        fail: false,
-    };
     let opts = PdfOcrOpts {
         enabled: true,
         always_on: true,
@@ -280,10 +237,7 @@ fn f6_flatedecode_skipped_with_warning() {
     let bytes = std::fs::read("../kebab-parse-pdf/tests/fixtures/flate_raw.pdf")
         .expect("F6 fixture missing");
     let mut canonical = canonical_with_empty_block(); // page-1 block from F1
-    let engine = MockOcrEngine {
+    let engine = MockOcrEngine::single("SHOULD_NOT_BE_CALLED", false);
-        expected_text: "SHOULD_NOT_BE_CALLED".into(),
-        fail: false,
-    };
     let opts = default_opts(true);
 
     let summary = apply_ocr_to_pdf_pages(&mut canonical, &engine, &bytes, &opts, |_| {}).unwrap();
@@ -307,10 +261,7 @@ fn f7_ccittfax_skipped_with_warning() {
     let bytes = std::fs::read("../kebab-parse-pdf/tests/fixtures/ccitt.pdf")
         .expect("F7 fixture missing");
     let mut canonical = canonical_with_empty_block(); // page-1 block from F1
-    let engine = MockOcrEngine {
+    let engine = MockOcrEngine::single("SHOULD_NOT_BE_CALLED", false);
-        expected_text: "SHOULD_NOT_BE_CALLED".into(),
-        fail: false,
-    };
     let opts = default_opts(true);
 
     let summary = apply_ocr_to_pdf_pages(&mut canonical, &engine, &bytes, &opts, |_| {}).unwrap();
@@ -330,10 +281,7 @@ fn f7_ccittfax_skipped_with_warning() {
 fn ocr_engine_failure_surfaces_as_warning() {
     let bytes = f1_pdf_bytes();
     let mut canonical = canonical_with_empty_block();
-    let engine = MockOcrEngine {
+    let engine = MockOcrEngine::single("", true);
-        expected_text: String::new(),
-        fail: true,
-    };
     let opts = default_opts(true);
 
     let summary = apply_ocr_to_pdf_pages(&mut canonical, &engine, &bytes, &opts, |_| {}).unwrap();
@@ -355,10 +303,7 @@ fn dual_block_ordinals_are_deterministic_and_unique() {
     let bytes = f1_pdf_bytes(); // 1-page PDF → page_count=1
     let text = "vector 충분한 텍스트. This text has more than twenty characters total.";
     let mut canonical = canonical_with_filled_block(text);
-    let engine = MockOcrEngine {
+    let engine = MockOcrEngine::single("DUAL", false);
-        expected_text: "DUAL".into(),
-        fail: false,
-    };
     let opts = PdfOcrOpts {
         enabled: true,
         always_on: true,
@@ -395,10 +340,7 @@ fn cancel_handle_aborts_mid_pdf() {
     let bytes = f1_pdf_bytes();
     let mut canonical = canonical_with_empty_block();
     let cancel = Arc::new(AtomicBool::new(true)); // pre-cancel
-    let engine = MockOcrEngine {
+    let engine = MockOcrEngine::single("IGNORED", false);
-        expected_text: "IGNORED".into(),
-        fail: false,
-    };
     let opts = PdfOcrOpts {
         enabled: true,
         always_on: false,